Classify Pixels using deep learning error 9999

605
3
11-28-2022 12:53 AM
Labels (2)
VincenzoDeriu
New Contributor

Hi,

I'm trying to reproduce the Esri Super Resolution algorithm sample: https://developers.arcgis.com/python/samples/increase-image-resolution-using-superresolution/

I've successfully created the dlpk model and I'm trying to use the "Classify Pixels Using Deep Learning" tool, but the tool fails with a generic error 999999.

ArcGIS Pro version is 2.9.5, I've tried with different raster sources, but the error is always the same. I don't know if it's a useful information, but I also have a warning: 

003054: Input Raster does not support PIXEL_SPACE (raw image space). Running in MAP_SPACE. 

 Does anyone have an idea on how to solve?

 

Thanks

0 Kudos
3 Replies
PavanYadav
Esri Contributor

@VincenzoDeriu 

003054 is supposed to be just a informative message to inform that Map_Space is being used. That means Spatial Reference information exist in the data and it will be used so it's in Map_Space. For example when your input raster (let's say an aerial image) has spatial reference information, the tools will use Map_Space. But, if your inputs images don't have spatial reference information for example street pictures taken from handheld camera, pixel_space will be used. 

003054: Input Raster does not support PIXEL_SPACE (raw image space). Running in MAP_SPACE.

You might find this doc useful: https://pro.arcgis.com/en/pro-app/latest/help/analysis/image-analyst/what-is-image-space-analysis-.h... 

But, I see the tool was failing with 999,999 error so there might be something else that was causing it to fail. Can you please share full message from the tool? If you have already fixed the issue, can you please share how you solved it? 

0 Kudos
VincenzoDeriu
New Contributor

Hi Pavan, unfortunately I've still not solved the isse and this is the only message I got from the tool.

0 Kudos
PavanYadav
Esri Contributor

@VincenzoDeriu My understanding this message is returned even after tool finishes successfully and outputs correct result. For you, does the tool finishes successfully fails with an error? From the History, can you use the Copy Python Command for your run and share the info. The copy will also copy over the error/any messages. I can take a look at. If you prefer, you can email me at pyadav at esri dot com. 

0 Kudos